© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 190
    Prev
    Next
    INDEX
    Explanations

    questions related to identifying specific information or asking for clarification

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     if
    -0.79
     when
    -0.77
     olsa
    -0.67
    when
    -0.65
     lorsque
    -0.63
    当
    -0.62
    if
    -0.62
    ِّف
    -0.62
     bahwa
    -0.61
    tsy
    -0.61
    POSITIVE LOGITS
     which
    3.72
    which
    3.34
     Which
    3.08
     WHICH
    3.06
    Which
    3.00
    hich
    2.16
     wich
    2.03
     laquelle
    1.82
     lequel
    1.80
     które
    1.77
    Activations Density 0.458%

    No Known Activations